From 54645c0b39f1b7dc653957ad16ed04c39b4e7ad2 Mon Sep 17 00:00:00 2001 From: Titouan Christophe Date: Sun, 1 Mar 2020 22:25:28 +0100 Subject: [PATCH] support/scripts/pkg-stats: clear multiprocessing pools after use During the CVE checking phase, we can still see a huge amount of Python processes (actually 128) running on the host, even though the CVE step is entirely ran in the main thread. These are actually the worker processes spawned to check for the packages URL statuses and the latest versions from release-monitoring. This is because of an issue in Python's multiprocessing implementation: https://bugs.python.org/issue34172 The problem was already there before the CVE matching step was introduced, but because pkg-stat was terminating right after the release-monitoring step, it went unnoticed. Also, do not hold a reference to the multiprocessing pool from the Package class, as this is not needed. Signed-off-by: Titouan Christophe Signed-off-by: Peter Korsgaard --- support/scripts/pkg-stats | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/support/scripts/pkg-stats b/support/scripts/pkg-stats index e414ec50f2..8a67e509e1 100755 --- a/support/scripts/pkg-stats +++ b/support/scripts/pkg-stats @@ -402,11 +402,13 @@ def check_url_status_worker(url, url_status): def check_package_urls(packages): - Package.pool = Pool(processes=64) + pool = Pool(processes=64) for pkg in packages: - pkg.url_worker = pkg.pool.apply_async(check_url_status_worker, (pkg.url, pkg.url_status)) + pkg.url_worker = pool.apply_async(check_url_status_worker, (pkg.url, pkg.url_status)) for pkg in packages: pkg.url_status = pkg.url_worker.get(timeout=3600) + del pkg.url_worker + pool.terminate() def release_monitoring_get_latest_version_by_distro(pool, name): @@ -479,6 +481,7 @@ def check_package_latest_version(packages): results = worker_pool.map(check_package_latest_version_worker, (pkg.name for pkg in packages)) for pkg, r in zip(packages, results): pkg.latest_version = r + worker_pool.terminate() del http_pool -- 2.30.2